Multi-agent collaborative perception

Abstract:
Single-agent perception has a number of inevitable limitations of single-agent perception, such as occlusion and long-range issues. To fundamentally address these, multi-agent collaborative perception is emerging. It enables multiple agents to share complementary perceptual information with each other, promoting more holistic perception. Related methods and systems are desperately needed in a broad range of real-world applications, especially vehicle-to-everything-communication-aided autonomous driving. This talk delves into the heart of this paradigm, spotlighting communication-adaptive collaborative perception.

Speaker's Bio:
Siheng Chen is a tenure-track associate professor of Shanghai Jiao Tong University. Before joining Shanghai Jiao Tong University, he was a research scientist at Mitsubishi Electric Research Laboratories (MERL), and an autonomy engineer at Uber Advanced Technologies Group (ATG), working on the perception and prediction systems of self-driving cars. Dr. Chen received his doctorate from Carnegie Mellon University. He has published over 80 papers on prestigious venues, including Nature Computational Science, Nature Scientific Data, T-PAMI,  T-SP,  T-IP, NeurIPS, ICML, ICLR and CVPR. Dr. Chen received the 2018 IEEE Signal Processing Society Young Author Best Paper Award, ASME SHM/NDE 2020 Best Journal Paper Runner-Up Award and the Best Student Paper Award at 2018 IEEE Global Conference on Signal and Information Processing, and MERL President's Award. His research interests include collective intelligence, graph machine learning and autonomous driving.